data-maker/data/gan.py

"""
usage :
    optional :
    --num_gpu   number of gpus to use will default to 1
    --epoch     steps per epoch default to 256
"""
import tensorflow as tf
from tensorflow.contrib.layers import l2_regularizer
import numpy as np
import pandas as pd
import time
import os
import sys
        Because prediction and training can happen independently
        """
            grad = tf.reduce_mean(grad, 0)

            v = grad_and_vars[0][1]
            grad_and_var = (grad, v)
            average_grads.append(grad_and_var)
        return average_grads        


class Generator (GNet):
    """
    This class is designed to handle generation of candidate datasets for this it will aggregate a discriminator, this allows the generator not to be random
    
    """
    def __init__(self,**args):
        GNet.__init__(self,**args)
        self.discriminator = Discriminator(**args)
    def loss(self,**args):
        fake    = args['fake']
        label   = args['label']
        y_hat_fake = self.discriminator.network(inputs=fake, label=label)
        all_regs = tf.get_collection(tf.GraphKeys.REGULARIZATION_LOSSES)
        loss = -tf.reduce_mean(y_hat_fake) + sum(all_regs)
        tf.add_to_collection('glosses', loss)
        return loss, loss        
    def load_meta(self, column):
        super().load_meta(column)
        self.discriminator.load_meta(column)
    def network(self,**args) :
        """
        This function will build the network that will generate the synthetic candidates
        :inputs matrix of data that we need
        :dim    dimensions of ...
        """
        x       = args['inputs']
        tmp_dim = self.Z_DIM if 'dim' not in args else args['dim']
        label   = args['label']
        
        with tf.compat.v1.variable_scope('G', reuse=tf.compat.v1.AUTO_REUSE , regularizer=l2_regularizer(0.00001)):
            for i, dim in enumerate(self.G_STRUCTURE[:-1]):
                kernel = self.get.variables(name='W_' + str(i), shape=[tmp_dim, dim])
                h1 = self.normalize(inputs=tf.matmul(x, kernel),shift=0, name='cbn' + str(i), labels=label, n_labels=self.NUM_LABELS)
                h2 = tf.nn.relu(h1)
                x = x + h2
                tmp_dim = dim
            i = len(self.G_STRUCTURE) - 1
            #
            # This seems to be an extra hidden layer: 
            # It's goal is to map continuous values to discrete values (pre-trained to do this)
            kernel = self.get.variables(name='W_' + str(i), shape=[tmp_dim, self.G_STRUCTURE[-1]])
            h1 = self.normalize(inputs=tf.matmul(x, kernel), name='cbn' + str(i),
                        labels=label, n_labels=self.NUM_LABELS)
            h2 = tf.nn.tanh(h1)
            x = x + h2
            # This seems to be the output layer
            #
            kernel = self.get.variables(name='W_' + str(i+1), shape=[self.Z_DIM, self.X_SPACE_SIZE])
            bias = self.get.variables(name='b_' + str(i+1), shape=[self.X_SPACE_SIZE])
            x = tf.nn.sigmoid(tf.add(tf.matmul(x, kernel), bias))
        return x       

class Discriminator(GNet):
    def __init__(self,**args):
        GNet.__init__(self,**args)     
    def network(self,**args):
        """
        This function will apply a computational graph on a dataset passed in with the associated labels and the last layer must have a single output (neuron)
        :inputs
        :label
        """
        x = args['inputs']
        print ()
        print (x[:3,:])
        print()
        label = args['label']
        with tf.compat.v1.variable_scope('D', reuse=tf.compat.v1.AUTO_REUSE , regularizer=l2_regularizer(0.00001)):
            for i, dim in enumerate(self.D_STRUCTURE[1:]):
                kernel = self.get.variables(name='W_' + str(i), shape=[self.D_STRUCTURE[i], dim])
                bias = self.get.variables(name='b_' + str(i), shape=[dim])
                print (["\t",bias,kernel])
                x = tf.nn.relu(tf.add(tf.matmul(x, kernel), bias))
                x = self.normalize(inputs=x, name='cln' + str(i), shift=1,labels=label, n_labels=self.NUM_LABELS)
            i = len(self.D_STRUCTURE)
            kernel = self.get.variables(name='W_' + str(i), shape=[self.D_STRUCTURE[-1], 1])
            bias = self.get.variables(name='b_' + str(i), shape=[1])
            y = tf.add(tf.matmul(x, kernel), bias)
        return y
    
    def loss(self,**args) :
        """
        This function compute the loss of 
        :real
        :fake
        :label
        """
        real    = args['real']
        fake    = args['fake']
        label   = args['label']
        epsilon = tf.random.uniform(shape=[self.BATCHSIZE_PER_GPU,1],minval=0,maxval=1)
        
        x_hat       = real + epsilon * (fake - real)
        y_hat_fake  = self.network(inputs=fake, label=label)
        
        y_hat_real  = self.network(inputs=real, label=label)
        y_hat       = self.network(inputs=x_hat, label=label)

        grad        = tf.gradients(y_hat, [x_hat])[0]
        slopes      = tf.sqrt(tf.reduce_sum(tf.square(grad), 1))
        gradient_penalty = tf.reduce_mean((slopes - 1.) ** 2)
        all_regs    = tf.get_collection(tf.GraphKeys.REGULARIZATION_LOSSES)
        w_distance  = -tf.reduce_mean(y_hat_real) + tf.reduce_mean(y_hat_fake)
        loss        = w_distance + 10 * gradient_penalty + sum(all_regs)
        tf.add_to_collection('dlosses', loss)

        return w_distance, loss        
class Train (GNet):
    def __init__(self,**args):
        GNet.__init__(self,**args)
        self.generator = Generator(**args)
        self.discriminator = Discriminator(**args)
        self._REAL = args['real']
        self._LABEL= args['label']
        self.generator.load_meta(column)
        dataset = dataset.batch(batch_size=self.BATCHSIZE_PER_GPU)
        dataset = dataset.prefetch(1)
        iterator = dataset.make_initializable_iterator()
        # next_element = iterator.get_next()
        # init_op = iterator.initializer
        return iterator, features_placeholder, labels_placeholder
    
    def network(self,**args):
    # def graph(stage, opt):
        # global_step = tf.get_variable(stage+'_step', [], initializer=tf.constant_initializer(0), trainable=False)
        stage   = args['stage']
        opt     = args['opt']
        tower_grads = []
        per_gpu_w   = []
        iterator, features_placeholder, labels_placeholder = self.input_fn()
        with tf.compat.v1.variable_scope(tf.compat.v1.get_variable_scope()):
            for i in range(self.NUM_GPUS):
                with tf.device('/gpu:%d' % i):
                    with tf.name_scope('%s_%d' % ('TOWER', i)) as scope:
                        (real, label) = iterator.get_next()
                        loss, w = self.loss(scope=scope, stage=stage, real=self._REAL, label=self._LABEL)
                        tf.get_variable_scope().reuse_variables()
                        vars_ = tf.get_collection(tf.GraphKeys.TRAINABLE_VARIABLES, scope=stage)
                        grads = opt.compute_gradients(loss, vars_)
                        tower_grads.append(grads)
                        per_gpu_w.append(w)

        grads = self.average_gradients(tower_grads)
        apply_gradient_op = opt.apply_gradients(grads)

        mean_w = tf.reduce_mean(per_gpu_w)
        train_op = apply_gradient_op
        return train_op, mean_w, iterator, features_placeholder, labels_placeholder
    def apply(self,**args):
        # max_epochs = args['max_epochs'] if 'max_epochs' in args else 10
        REAL = self._REAL
        LABEL= self._LABEL       
        with tf.device('/cpu:0'):
            opt_d = tf.compat.v1.train.AdamOptimizer(1e-4)
            opt_g = tf.compat.v1.train.AdamOptimizer(1e-4)
            
            train_d, w_distance, iterator_d, features_placeholder_d, labels_placeholder_d = self.network(stage='D', opt=opt_d)
            train_g, _, iterator_g, features_placeholder_g, labels_placeholder_g = self.network(stage='G', opt=opt_g)
            # saver = tf.train.Saver()
            saver   = tf.compat.v1.train.Saver()
            init    = tf.global_variables_initializer()

            with tf.Session(config=tf.ConfigProto(allow_soft_placement=True, log_device_placement=False)) as sess:
                sess.run(init)
                sess.run(iterator_d.initializer,
                        feed_dict={features_placeholder_d: REAL, labels_placeholder_d: LABEL})
                sess.run(iterator_g.initializer,
                        feed_dict={features_placeholder_g: REAL, labels_placeholder_g: LABEL})

                for epoch in range(1, self.MAX_EPOCHS + 1):
                    start_time = time.time()
                    w_sum = 0
                    for i in range(self.STEPS_PER_EPOCH):
                        for _ in range(2):
                            _, w = sess.run([train_d, w_distance])
                            w_sum += w
                        sess.run(train_g)
                    duration = time.time() - start_time

                    assert not np.isnan(w_sum), 'Model diverged with loss = NaN'

                    format_str = 'epoch: %d, w_distance = %f (%.1f)'
                    print(format_str % (epoch, -w_sum/(self.STEPS_PER_EPOCH*2), duration))
                    if epoch % self.MAX_EPOCHS == 0:
    """
        print (__doc__)
    pass